{"record": {"aliases": ["Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language"], "artifacts": [{"id": "arxiv:2609.03677", "kind": "paper", "url": "https://arxiv.org/abs/2609.03677"}, {"id": "gh:kit-mrt/ad-diff", "kind": "repo", "url": "https://github.com/KIT-MRT/AD-Diff"}], "authors": ["Julian Truetsch", "Felix Hauser", "Christoph Stiller", "Frank Bieder"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.03677", "source_url": "https://arxiv.org/abs/2609.03677"}, "categories": ["Autonomous Driving", "General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates set-difference captioning on autonomous driving image subsets, with three splits based on annotation filtering, CLIP filtering, and web scraping, yielding natural-language descriptions of differences between target and reference sets."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.03677", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.03677", "title": "AD-Diff Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Karlsruhe Institute of Technology", "FZI Research Center for Information Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.03677", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.03677", "source_url": "https://openalex.org/W7208792383"}, "key": "claire-radar:2609.03677", "modality": null, "name": "AD-Diff Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_understanding-autonomous-driving-datasets-_149f7829", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "dfbec6f6ba3a07abeb17ad1b9cdba1a4c27afa6cc71d6c022c9251e6b412debf", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-07T00:42:15.394147Z", "source_url": "https://arxiv.org/abs/2609.03677"}, "publisher": null, "released": "2026-09-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.03677", "source_url": "https://arxiv.org/abs/2609.03677"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-03677", "source": "claire_radar", "source_benchmark_id": "2609.03677", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language"], "annotation": "Unknown", "applicationDomains": ["General AI", "Autonomous Driving"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-04", "attemptedAt": "2026-09-04T06:36:46.783164Z", "githubRepo": "https://github.com/KIT-MRT/AD-Diff", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.03677", "observedAt": "2026-09-04T06:36:46.783164Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-04T06:36:46.783164Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-04T06:36:46.783164Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The paper targets a niche intersection of autonomous driving and dataset interpretability with an available code release, likely drawing moderate attention from multimodal evaluation researchers but limited broader interest.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-07T00:42:15.394147Z", "inputHash": "eb4340486ad9384bf7238555bfcee131537ce07777516f555743433bc1d5504c", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "To evaluate this setting in-domain, we introduce a new benchmark, AD-Diff Bench.", "canonicalNameSource": "abstract", "decisionReason": "Formally introduced as a benchmark with a released dataset, public code, and a defined evaluation protocol for set-difference captioning, satisfying reuse and scoring criteria.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-07T00:42:15.394147Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates set-difference captioning on autonomous driving image subsets, with three splits based on annotation filtering, CLIP filtering, and web scraping, yielding natural-language descriptions of differences between target and reference sets.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To evaluate this setting in-domain, we introduce a new benchmark, AD-Diff Bench."}, "familyId": "bmf_f0f0dfe79110", "firstSeenAt": "2026-09-04", "heat": null, "id": "bm_understanding-autonomous-driving-datasets-_149f7829", "indexedAt": "2026-09-04T06:13:54.443310Z", "industrySectors": ["Automotive"], "links": {"code": "https://github.com/KIT-MRT/AD-Diff", "data": null, "paper": "https://arxiv.org/abs/2609.03677", "pdf": "https://arxiv.org/pdf/2609.03677", "project": null, "report": "https://arxiv.org/abs/2609.03677"}, "metrics": [], "motivation": "Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains.", "name": "AD-Diff Bench", "oneLine": "Evaluates set-difference captioning on autonomous driving image subsets, with three splits based on annotation filtering, CLIP filtering, and web scraping, yielding natural-language descriptions of differences between target and reference sets.", "paperTitle": "Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.03677", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-04T06:13:54.443310Z"}, "publications": [], "publishers": [{"name": "KIT-MRT", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/KIT-MRT/AD-Diff"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.10323645750017778, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 93, "score": 28}, "method": "attention-ranking-v13", "rank": 93, "score": 28}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.09399878027980717, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 255, "score": 28}, "method": "attention-ranking-v13", "rank": 255, "score": 28}, "today": {"confidence": "Low", "coverage": 0.25, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 1, "historyDate": "2026-09-03", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": 0.7142857142857143, "percentile": 0.7142857142857143, "value": 1}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.48, "role": "bonus", "value": 48}}, "confidence": "Low", "coverage": 0.25, "rank": 4, "score": 55}, "method": "attention-ranking-v13", "rank": 4, "score": 55}}, "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-09-03", "source": {"authors": ["Julian Truetsch", "Felix Hauser", "Christoph Stiller", "Frank Bieder"], "categories": ["cs.CV", "cs.CL", "cs.LG", "cs.NE", "cs.RO"], "id": "2609.03677", "title": "Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language", "type": "arxiv", "url": "https://arxiv.org/abs/2609.03677"}, "sourceUpdatedAt": "2026-09-03T11:15:23Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Provides a human-interpretable way to audit domain shift and dataset composition in autonomous driving, moving beyond metadata to object-attributed semantic differences that matter for safety and robustness."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
